Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific locations or routes mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific road routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oted
    -0.81
    framework
    -0.76
    */(
    -0.72
    merce
    -0.72
    esome
    -0.72
    cious
    -0.71
    aum
    -0.70
    olded
    -0.70
    razil
    -0.69
    estation
    -0.68
    POSITIVE LOGITS
     Route
    1.19
    Route
    0.93
    route
    0.88
     Road
    0.84
     Parkway
    0.82
     route
    0.81
     Highway
    0.81
     routes
    0.80
     Corridor
    0.78
     Avenue
    0.76
    Act Density 0.013%

    No Known Activations